Výsledky vyhľadávania - Gradient-based learning algorithm

Convergence analysis of the batch gradient-based neuro-fuzzy learning algorithm with smoothing L 1/2 regularization for the first-order Takagi–Sugeno system Autor Liu, Yan, Yang, Dakun

Získať plný text

A Novel Fractional Gradient-Based Learning Algorithm for Recurrent Neural Networks Autor Khan, Shujaat, Ahmad, Jawwad, Naseem, Imran, Moinuddin, Muhammad

“…In this research, we propose a novel algorithm for learning of the recurrent neural networks called as the fractional back-propagation through time (FBPTT…”
Získať plný text

A supervised gradient-based learning algorithm for optimized entity resolution Autor Reyes-Galaviz, Orion F., Pedrycz, Witold, He, Ziyue, Pizzi, Nick J.

“…The task of probabilistic record linkage is to find and link records that refer to the same entity across several disparate data sources. The accurate linking…”
Získať plný text

Convergence of a modified gradient-based learning algorithm with penalty for single-hidden-layer feed-forward networks Autor Wang, Jian, Zhang, Bingjie, Sang, Zhaoyang, Liu, Yusong, Wu, Shujun, Miao, Quan

“…Based on a novel algorithm, known as the upper-layer-solution-aware (USA), a new algorithm, in which the penalty method is introduced into the empirical risk…”
Získať plný text

Convergence of a Gradient-Based Learning Algorithm With Penalty for Ridge Polynomial Neural Networks Autor Fan, Qinwei, Peng, Jigen, Li, Haiyang, Lin, Shoujin

“…Recently there have been renewed interests in high order neural networks (HONNs) for its powerful mapping capability. Ridge polynomial neural network (RPNN) is…”
Získať plný text

Joint Optimization of Concave Scalarized Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm Autor Bai, Qinbo, Agarwal, Mridul, Aggarwal, Vaneet

“… A policy-gradient based model-free algorithm is proposed for the problem. To compute an estimate of the gradient, an asymptotically biased estimator is proposed…”
Získať plný text

Strong Convergence Analysis of Batch Gradient-Based Learning Algorithm for Training Pi-Sigma Network Based on TSK Fuzzy Models Autor Liu, Yan, Yang, Dakun, Nan, Nan, Guo, Li, Zhang, Jianjun

“… The aim of this paper is to present a gradient-based learning method for Pi-Sigma network to train TSK fuzzy inference system…”
Získať plný text

Short-term scheduling of thermal power systems using hybrid gradient based modified teaching–learning optimizer with black hole algorithm Autor Azizipanah-Abarghooee, Rasoul, Niknam, Taher, Bavafa, Farhad, Zare, Mohsen

“…•Consider operating reserve, line flow limits and transmission losses in the formula.•Propose a new gradient-based MTLBO–BH…”
Získať plný text

Variable learning adaptive gradient based control algorithm for voltage source converter in distributed generation Autor Giri, Ashutosh K, Arya, Sabha Raj, Maurya, Rakesh, Mehar, Ramakanta

“…This study presents an adaptive control algorithm known as variable learning and adaptive gradient based least mean square for improving the power quality features in standalone distributed generation…”
Získať plný text

A modified gradient-based neuro-fuzzy learning algorithm and its convergence Autor Wu, Wei, Li, Long, Yang, Jie, Liu, Yan

“… In this paper, a modified gradient-based neuro-fuzzy learning algorithm is proposed for zero-order Takagi…”
Získať plný text

A Gradient-Based Reinforcement Learning Algorithm for Multiple Cooperative Agents Autor Zhang, Zhen, Wang, Dongqing, Zhao, Dongbin, Han, Qiaoni, Song, Tingting

“…Multi-agent reinforcement learning (MARL) can be used to design intelligent agents for solving cooperative tasks…”
Získať plný text

Convergence analysis of the batch gradient-based neuro-fuzzy learning algorithm with smoothing L1/2 regularization for the first-order Takagi–Sugeno system Autor Liu, Yan, Yang, Dakun

“… The neuro-fuzzy learning algorithm involves two tasks: generating comparable sparse networks and training the parameters…”
Získať plný text

Neurofuzzy-Based Plant-Wide Hierarchical Coordinating Optimization and Control: An Application to Zinc Hydrometallurgy Plant Autor Xie, Shiwen, Xie, Yongfang, Ying, Hao, Jiang, Zhaohui, Gui, Weihua

“…) is used in this layer. Also used are FNNs with a gradient-based learning algorithm, which are trained to represent the models of the processes…”
Získať plný text

An Analytic Policy Gradient-Based Deep Reinforcement Learning Motion Cueing Algorithm for Driving Simulators Autor Huang, Xiaowei, Shi, Xuhua, Wang, Peiyao, Xu, Hongzan, Tang, Xiaojun, Zhang, Gaoran

“…The proposed motion cueing algorithm (MCA), based on a reinforcement learning algorithm using gradient information to directly update the control policy, introduces three significant enhancements…”
Získať plný text

Short-term load forecasting of Australian National Electricity Market by an ensemble model of extreme learning machine Autor Zhang, Rui, Dong, Zhao Yang, Xu, Yan, Meng, Ke, Wong, Kit Po

“… However, traditional ANNs are mostly trained by gradient-based learning algorithms which usually suffer from excessive training and tuning burden as well as unsatisfactory generalization performance…”
Získať plný text

Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review Autor Kaveh, Mehrdad, Mesgari, Mohammad Saadi

“…) architectures is considered one of the most challenging machine learning problems. Several past studies have used gradient-based back propagation methods to train DL architectures…”
Získať plný text

Multi-agent Gradient-Based Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning Autor Ren, Jineng

“…This paper proposes a gradient-based multi-agent actor-critic algorithm for off-policy reinforcement learning using importance sampling…”
Získať plný text

Object Detection via Gradient-Based Mask R-CNN Using Machine Learning Algorithms Autor Xavier, Alphonse Inbaraj, Villavicencio, Charlyn, Macrohon, Julio Jerison, Jeng, Jyh-Horng, Hsieh, Jer-Guang

“…++) for localization and Mask Regional Convolution Neural Network (Mask R-CNN) for object detection along with machine learning algorithms…”
Získať plný text

Deep Deterministic Policy Gradient Algorithm Based Reinforcement Learning Controller for Single-Inductor Multiple-Output DC-DC Converter Autor Ye, Jian, Guo, Huanyu, Wang, Benfei, Zhang, Xinan

“… In this article, we propose a deep deterministic policy gradient algorithm based reinforcement learning (RL) controller…”
Získať plný text

A servo system control with time-varying and nonlinear load conditions using type-2 TSK fuzzy neural system Autor Kayacan, Erdal, Oniz, Yesim, Aras, Ayse Cisel, Kaynak, Okyay, Abiyev, Rahib

“…A type-2 Takagi-Sugeno-Kang fuzzy neural system is proposed and its parameter update rules are derived using fuzzy clustering and gradient learning algorithms…”
Získať plný text